mlsanityData to 14 Oct 2026

Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models

arXiv 2502.11619 ↗First posted 17 Feb 2025cs.CVcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-tuning a Latent Diffusion Model (LDM). A Membership Inference Attack (MIA) method is presented for this task. Using generated auxiliary data for the training of the attack model leads to significantly better performance, and so does the use of watermarks. The guidance scale used for inference was found to have a significant influence. If a LDM is fine-tuned for long enough, the text prompt used for inference has no significant influence. The proposed MIA is found to be viable in a realistic black-box setup against LDMs fine-tuned on face-images.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 7 of its 9 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

7 of 9 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Towards More Realistic Membership Inference Attacks on Large Diffusion Models22 Jun
  2. 2023Extracting Training Data from Diffusion Models30 Jan

Other references · 5

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Identity-Focused Inference and Extraction Attacks on Diffusion Models
  2. 2025Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
  3. 2026Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise
  4. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
  5. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?
  6. 2026Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models
  7. 2024Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models
  8. 2024Towards Black-Box Membership Inference Attack for Diffusion Models